This seems to be more common in LLVM, Google and Chromium.
Before:
class AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA :
public BBBBBBBBBBBBBBBBBBBBBBBBBBBBBB,
public CCCCCCCCCCCCCCCCCCCCCCCCCCCCCC {
};
After:
class AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
: public BBBBBBBBBBBBBBBBBBBBBBBBBBBBBB,
public CCCCCCCCCCCCCCCCCCCCCCCCCCCCCC {
};
llvm-svn: 181183
I was not able to find a case (other than the fix in r181163) where this
makes a difference, but it is a more obviously correct API to have.
llvm-svn: 181165
to use. This makes very little difference right now (other than suppressing
follow-on errors in some cases), but will matter more once we support deduced
return types (we don't want expressions with undeduced return types in the
AST).
llvm-svn: 181107
This change required some minor changes to LocationContextMap to have it map
from PathPieces to LocationContexts instead of PathDiagnosticCallPieces to
LocationContexts. These changes are in the other diagnostic
generation logic as well, but are functionally equivalent.
Interestingly, this optimize requires delaying "cleanUpLocation()" until
later; possibly after all edges have been optimized. This is because
we need PathDiagnosticLocations to refer to the semantic entity (e.g. a statement)
as long as possible. Raw source locations tell us nothing about
the semantic relationship between two locations in a path.
llvm-svn: 181084
Previously, we would clone the current diagnostic consumer to produce
a new diagnostic consumer to use when building a module. The problem
here is that we end up losing diagnostics for important diagnostic
consumers, such as serialized diagnostics (where we'd end up with two
diagnostic consumers writing the same output file). With forwarding,
the diagnostics from all of the different modules being built get
forwarded to the one serialized-diagnostic consumer and are emitted in
a sane way.
Fixes <rdar://problem/13663996>.
llvm-svn: 181067
Un-break the gdb buildbot.
- Use the debug location of the return expression for the cleanup code
if the return expression is trivially evaluatable, regardless of the
number of stop points in the function.
- Ensure that any EH code in the cleanup still gets the line number of
the closing } of the lexical scope.
- Added a testcase with EH in the cleanup.
rdar://problem/13442648
llvm-svn: 181056
Add serialization for captured statements and captured decls. Also add
a const_capture_iterator to CapturedStmt.
Test contributed by Wei Pan
Differential Revision: http://llvm-reviews.chandlerc.com/D727
llvm-svn: 181048
Move the creation of CapturedStmt parameters out of CodeGen and into
Sema, making it easier to customize the outlined function. The
ImplicitParamDecls are stored in the CapturedDecl using an
ASTContext-allocated array.
Differential Revision: http://llvm-reviews.chandlerc.com/D722
llvm-svn: 181043
MSVC provides __wchar_t, either as an alias for the built-in wchar_t
type, or as a separate type depending on language (C vs C++) and flags
(-fno-wchar).
In -fms-extensions, Clang will simply accept __wchar_t as an alias for
whatever type is used for wide character literals. In -fms-compatibility, we
try to mimic MSVC's behavior by always making __wchar_t a builtin type.
This fixes PR15815.
llvm-svn: 181004
a lambda.
Bug #1 is that CGF's CurFuncDecl was "stuck" at lambda invocation
functions. Fix that by generally improving getNonClosureContext
to look through lambdas and captured statements but only report
code contexts, which is generally what's wanted. Audit uses of
CurFuncDecl and getNonClosureAncestor for correctness.
Bug #2 is that lambdas weren't specially mapping 'self' when inside
an ObjC method. Fix that by removing the requirement for that
and using the normal EmitDeclRefLValue path in LoadObjCSelf.
rdar://13800041
llvm-svn: 181000
FindLastStoreBRVisitor is responsible for finding where a particular region
gets its value; if the region is a VarRegion, it's possible that value was
assigned at initialization, i.e. at its DeclStmt. However, if a function is
called recursively, the same DeclStmt may be evaluated multiple times in
multiple stack frames. FindLastStoreBRVisitor was not taking this into
account and just picking the first one it saw.
<rdar://problem/13787723>
llvm-svn: 180997
There were actually two bugs here:
- if we decided to look for an interesting lvalue or call expression, we
wouldn't go find its node if we also knew we were at a (different) call.
- if we looked through one message send with a nil receiver, we thought we
were still looking at an argument to the original call.
Put together, this kept us from being able to track the right values, which
means sub-par diagnostics and worse false-positive suppression.
Noticed by inspection.
llvm-svn: 180996
Without any conversion, this is pretty straightforward. Most of the
fields can be zeros. The order is:
- field offset or pointer
- nonvirtual adjustment (for MI functions)
- vbptr offset (for unspecified)
- virtual adjustment offset (for virtual inheritance)
Differential Revision: http://llvm-reviews.chandlerc.com/D699
llvm-svn: 180985
- Use the debug location of the return expression for the cleanup code
if the return expression is trivially evaluatable, regardless of the
number of stop points in the function.
- Ensure that any EH code in the cleanup still gets the line number of
the closing } of the lexical scope.
- Added a testcase with EH in the cleanup.
rdar://problem/13442648
llvm-svn: 180982
the actual parser and support arbitrary id-expressions.
We're actually basically set up to do arbitrary expressions here
if we wanted to.
Assembly operands permit things like A::x to be written regardless
of language mode, which forces us to embellish the evaluation
context logic somewhat. The logic here under template instantiation
is incorrect; we need to preserve the fact that an expression was
unevaluated. Of course, template instantiation in general is fishy
here because we have no way of delaying semantic analysis in the
MC parser. It's all just fishy.
I've also fixed the serialization of MS asm statements.
This commit depends on an LLVM commit.
llvm-svn: 180976
BugReporter is used to process ALL bug reports. By using a shared map,
we are having mappings from different PathDiagnosticPieces to LocationContexts
well beyond the point where we are processing a given report. This
state is inherently error prone, and is analogous to using a global
variable. Instead, just create a temporary map, one per report,
and when we are done with it we throw it away. No extra state.
llvm-svn: 180974
This change partly addresses a heinous problem we have with the
parsing of attribute arguments that are a lone identifier. Previously,
we would end up parsing the 'align' attribute of this as an expression
"(Align)":
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align((Align)))) char storage[Size];
};
while this would parse as a "parameter name" 'Align':
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align(Align))) char storage[Size];
};
The code that handles the alignment attribute would completely ignore
the parameter name, so the while the first of these would do what's
expected, the second would silently be equivalent to
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align)) char storage[Size];
};
i.e., use the maximal alignment rather than the specified alignment.
Address this by sniffing the "Args" provided in the TableGen
description of attributes. If the first argument is "obviously"
something that should be treated as an expression (rather than an
identifier to be matched later), parse it as an expression.
Fixes <rdar://problem/13700933>.
llvm-svn: 180973
This change partly addresses a heinous problem we have with the
parsing of attribute arguments that are a lone identifier. Previously,
we would end up parsing the 'align' attribute of this as an expression
"(Align)":
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align((Align)))) char storage[Size];
};
while this would parse as a "parameter name" 'Align':
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align(Align))) char storage[Size];
};
The code that handles the alignment attribute would completely ignore
the parameter name, so the while the first of these would do what's
expected, the second would silently be equivalent to
template<unsigned Size, unsigned Align>
class my_aligned_storage
{
__attribute__((align)) char storage[Size];
};
i.e., use the maximal alignment rather than the specified alignment.
Address this by sniffing the "Args" provided in the TableGen
description of attributes. If the first argument is "obviously"
something that should be treated as an expression (rather than an
identifier to be matched later), parse it as an expression.
Fixes <rdar://problem/13700933>.
llvm-svn: 180970
...and don't consider '0' to be a null pointer constant if it's the
initializer for a float!
Apparently null pointer constant evaluation looks through both
MaterializeTemporaryExpr and ImplicitCastExpr, so we have to be more
careful about types in the callers. For RegionStore this just means giving
up a little more; for ExprEngine this means handling the
MaterializeTemporaryExpr case explicitly.
Follow-up to r180894.
llvm-svn: 180944
After some discussion, it was decided to use the Itanium ABI for thread_local on
Darwin OS X platforms. This involved a couple of changes. First, we use
"_tlv_atexit" instead of "__cxa_thread_atexit". Secondly, the global variables
are marked with 'internal' linkage, because we want all access to be calls to
the Itanium-specific entry point, which has normal linkage.
<rdar://problem/13733006>
llvm-svn: 180941
The "magical" builtin headers are the headers we provide as part of
the C standard library, which typically comes from /usr/include. We
essentially merge our headers into that location (due to cyclic
dependencies). This change makes sure that, when header search finds
one of our builtin headers, we figure out which module it actually
lives in. This case is fairly rare; one ends up having to include one
of the few built-in C headers we provide before including anything
from /usr/include to trigger it. Fixes <rdar://problem/13787184>.
llvm-svn: 180934
If there is cleanup code, the cleanup code gets the debug location of
the closing '}'. The subsequent ret IR-instruction does not get a
debug location. The return _expression_ will get the debug location
of the return statement.
If the function contains only a single, simple return statement,
the cleanup code may become the first breakpoint in the function.
In this case we set the debug location for the cleanup code
to the location of the return statement.
rdar://problem/13442648
llvm-svn: 180932
This adds a test to make sure we define _WCHAR_T_DEFINED and
_NATIVE_WCHAR_T_DEFINED correctly in the preprocessor, and updates
stddef.h to set it when typedeffing wchar_t.
llvm-svn: 180918
It is unfortunate that we have to mark these exceptions in multiple places.
This was already in CallEvent. I suppose it does let us be more precise
about saying /which/ arguments have their retain counts invalidated -- the
connection's is still valid even though the context object's isn't -- but
we're not tracking the retain count of XPC objects anyway.
<rdar://problem/13783514>
llvm-svn: 180904
Previously, this was scattered across Environment (literal expressions),
ExprEngine (default arguments), and RegionStore (global constants). The
former special-cased several kinds of simple constant expressions, while
the latter two deferred to the AST's constant evaluator.
Now, these are all unified as SValBuilder::getConstantVal(). To keep
Environment fast, the special cases for simple constant expressions have
been left in, but the main benefits are that (a) unusual constants like
ObjCStringLiterals now work as default arguments and global constant
initializers, and (b) we're not duplicating code between ExprEngine and
RegionStore.
This actually caught a bug in our test suite, which is awesome: we stop
tracking allocated memory if it's passed as an argument along with some
kind of callback, but not if the callback is 0. We were testing this in
a case where the callback parameter had a default value, but that value
was 0. After this change, the analyzer now (correctly) flags that as a
leak!
<rdar://problem/13773117>
llvm-svn: 180894
This goes with r178516, which instructed the analyzer not to inline the
constructors and destructors of C++ container classes. This goes a step
further and does the same thing for iterators, so that the analyzer won't
falsely decide we're trying to construct an iterator pointing to a
nonexistent element.
The heuristic for determining whether something is an iterator is the
presence of an 'iterator_category' member. This is controlled under the
same -analyzer-config option as container constructor/destructor inlining:
'c++-container-inlining'.
<rdar://problem/13770187>
llvm-svn: 180890
temporary to an lvalue before taking its address. This removes a weird special
case from the AST representation, and allows the constant expression evaluator
to deal with it without (broken) hacks.
llvm-svn: 180866
This doesn't appear to be the cause of the slowdown. I'll have to try a
manual bisect to see if there's really anything there, or if it's just
the bot itself taking on additional load. Meanwhile, this change helps
with correctness.
This changes an assertion and adds a test case, then re-applies r180638,
which was reverted in r180714.
<rdar://problem/13296133> and PR15863
llvm-svn: 180864
Previously it would point to the left bracket or the receiver, which can be particularly
problematic if the receiver is a block literal and we end up point the diagnostic far away
for the selector that is complaining about.
rdar://13620447
llvm-svn: 180833
Original commit message:
Emit the TLS intialization functions into a list.
Add the TLS initialization functions to a list of initialization functions. The
back-end takes this list and places the function pointers into the correct
section. This way they're called before `main().'
<rdar://problem/13733006>
llvm-svn: 180809
Summary:
Like Itanium, comparisons are basically bitwise comparisons of the two
values, with an exception for null member function pointers. If two
function pointers are null, only the function pointer field matters for
comparison purposes. The rest of the bits can be arbitrary. We take
advantage of this in isZeroInitializable(), and it may matter once we
start emitting conversions.
Reviewers: rjmccall
CC: cfe-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D695
llvm-svn: 180800
are now two distinct canonical 'AutoType's: one is the undeduced 'auto'
placeholder type, and the other is a deduced-but-dependent type. All
deduced-to-a-non-dependent-type cases are still non-canonical.
llvm-svn: 180789
Richard Smith